Best Input Price
$0.06 / 1M
Open-weight hybrid model for enterprise chat, coding, retrieval-augmented generation, and tool-calling workloads
Context Window
131,072 tokens
Reasoning
No
Tool Calling
Supported
Released
2025-10-02
Inference Providers (1)
| Provider | Model ID | Context | Input / 1M | Output / 1M | Action |
|---|---|---|---|---|---|
| watsonx.ai | ibm/granite-4-h-small | 131,072 | $0.06 | $0.27 | Docs ↗ |